Generative AI in Healthcare: Advancements in

Electronic Health Records, facilitating Medical

JAAHMM
Journal of Advanced Analytics in
Healthcare Management Languages, and Personalized Patient Care

Kannan Nova

Abstract
This research explores the application of generative AI techniques in
healthcare to address three significant areas: enhancing electronic health
records (EHRs) through automated conversation summarization, simplifying
complex medical language into patient-friendly summaries, and providing
personalized care recommendations using data from smartwatches and
wearables. In the first part, we propose a technical framework for utilizing
generative AI to listen to conversations during healthcare appointments and
generate concise summaries for inclusion in EHRs. The process involves
speech recognition, natural language processing (NLP), named entity
recognition (NER), contextual understanding, text summarization, and
seamless integration with EHR systems. The implementation of such a system
requires rigorous evaluation, training data, and adherence to healthcare
regulations. The second part focuses on simplifying complex medical language
into summaries that patients can understand. We present a technical sequence
flow that involves data collection, preprocessing, training data preparation,
model selection, architecture, training, evaluation, fine-tuning, deployment,
user interaction, summary generation, output presentation, and feedback
iteration. By employing generative AI models trained on medical documents,
patients can access simplified and understandable summaries, improving
patient education and communication in healthcare settings. Lastly, we explore
the utilization of generative AI for personalized care recommendations using
data from smartwatches and wearables. Its technical sequence flow
encompasses data collection, data transfer to the cloud, data preprocessing,
data analysis with generative AI, personalized care recommendations, delivery
of recommendations, user interaction, and feedback. By analyzing sensor data,
generative AI models can generate personalized recommendations for exercise,
diet, sleep, and medication, enhancing individualized care for users.

Keywords: Generative AI, Conversation summarization, Electronic health record (EHR),

Speech recognition, Natural Language Processing (NLP), Named Entity Recognition
(NER), Personalized care recommendations

Introduction
Generative Artificial Intelligence (AI) has seen significant
advancements and evolution over the years, revolutionizing various
domains such as computer vision, natural language processing, and
creative arts [1], [2]. The roots of generative AI can be traced back to
the early days of AI research when pioneers like Alan Turing and John

115
JAAHM
Journal of Advanced Analytics in
Healthcare Management

von Neumann laid the foundations. However, it was not until the 1990s
that generative models gained traction with the emergence of Bayesian
networks and Hidden Markov Models. These models enabled the
generation of new data based on probabilistic principles and laid the
groundwork for future developments in generative AI [3], [4].
The field of generative AI took a major leap forward with the
introduction of Generative Adversarial Networks (GANs) by Ian
Goodfellow and his colleagues in 2014. GANs consist of two neural
networks, a generator and a discriminator, which engage in a game-
theoretic process to generate realistic data. This breakthrough brought
about a significant shift in generative AI, enabling the generation of
highly realistic images, videos, and even text [5]–[7]. GANs have
since been widely adopted and improved, leading to the creation of
visually stunning deepfake videos, image synthesis, and style transfer
applications.
Another significant milestone in the evolution of generative AI came
with the introduction of Variational Autoencoders (VAEs). VAEs,
proposed by Kingma and Welling in 2013, combine the power of neural
networks with the principles of variational inference [8]–[10]. VAEs
allow for the generation of new data by learning a lower-dimensional
latent space representation of the input data. This latent space can then
be sampled to generate new instances that resemble the original data
distribution. VAEs have found applications in diverse areas such as
image generation, music composition, and drug discovery. In recent
years, the concept of transformers, introduced by Vaswani et al. in 2017,
has made a significant impact on generative AI. Transformers, based on
the attention mechanism, revolutionized natural language processing
tasks by enabling efficient processing of sequential data [11].
Generative Artificial Intelligence (AI) models are distinct from other
AI models based on their primary objective of generating new data
samples that resemble a given training dataset. Unlike discriminative
models, which focus on classification and decision-making tasks,
generative models aim to capture the underlying distribution of the data
and generate new instances that follow that distribution. Generative
models allow for the creation of new content, such as images, videos,
music, and text, while maintaining coherence and similarity to the
original data [12]. This ability to generate novel content sets
generative AI apart from other AI models, making it suitable for
creative applications and data augmentation tasks.
The core principles and techniques behind generative AI revolve
around modeling the underlying probability distribution of the data.
Two fundamental approaches are widely used: Generative Adversarial
116 | P a g e J. Adv. Analytics Healthc. Manage.
JAAHM
Journal of Advanced Analytics in
Healthcare Management

Networks (GANs) and Variational Autoencoders (VAEs). GANs

involve training a generator network to produce synthetic data and a
discriminator network to distinguish between real and generated
samples. The generator improves its ability to generate realistic data by
competing against the discriminator. VAEs, on the other hand, focus on
learning the latent space representation of the input data and
generating new instances by sampling from this learned distribution.
VAEs utilize the principles of variational inference to encode and
decode data samples [13].
Generative AI models incorporate various components and
architectures to achieve their objectives. In GANs, the generator
network takes random noise as input and transforms it into synthetic
data. It typically consists of multiple layers, such as convolutional layers
for image data or recurrent layers for sequential data. The discriminator
network, often a convolutional neural network (CNN) or a feed-forward
network, assesses the authenticity of the generated samples [13], [14].
The two networks are trained simultaneously in an adversarial manner.
For VAEs, the encoder network maps input data to a lower-dimensional
latent space, capturing the essence of the data. The decoder network
then reconstructs the original data from the latent space representation.
Both the encoder and decoder networks can be implemented using
various neural network architectures, such as fully connected layers or
convolutional layers.
Additionally, other architectures like autoregressive models, such as
PixelRNN and WaveNet, generate data by modeling the conditional
probability of each data point given its preceding context. These models
generate data sequentially, often used for tasks like image generation
or text generation.
Early AI systems focused on rule-based expert systems that attempted
to mimic human decision-making processes. These systems relied on
predefined rules and logical deductions to provide diagnostic
suggestions or treatment plans. However, due to the limited
computational power and the lack of large-scale medical data, these
early attempts faced significant challenges.
In the 1990s and early 2000s, with the advent of more powerful
computers and the availability of large medical datasets, AI in
healthcare started gaining momentum [15]. Machine learning
techniques such as neural networks, decision trees, and support vector
machines were employed to analyze vast amounts of medical data and
extract meaningful patterns. This led to the development of AI
applications for medical imaging, such as computer-aided diagnosis
117 | P a g e J. Adv. Analytics Healthc. Manage.
JAAHM
Journal of Advanced Analytics in
Healthcare Management

(CAD) systems, which could detect abnormalities in medical images

with high accuracy. Additionally, AI algorithms were utilized for drug
discovery, genomics research, and personalized medicine. These
advancements opened up new possibilities for improving diagnostics,
treatment planning, and patient outcomes.
In recent years, the evolution of AI in healthcare has been driven by the
convergence of various technologies and the exponential growth of
healthcare data. The rise of deep learning, a subset of machine learning,
has revolutionized AI applications in healthcare. Deep learning
algorithms, particularly convolutional neural networks (CNNs) and
recurrent neural networks (RNNs), have demonstrated remarkable
performance in medical image analysis, natural language processing,
and predictive analytics. AI is being used to assist radiologists in
detecting and diagnosing diseases from medical images, to analyze
electronic health records (EHRs) for predictive analytics and clinical
decision support, and to develop precision medicine approaches based
on individual patient characteristics. The integration of AI with other
emerging technologies like Internet of Things (IoT) devices, wearable
sensors, and robotics holds the promise of further advancements in in
every industry [16], including remote patient monitoring,
telemedicine, and surgical assistance [17]–[19].

Generative AI in Electronic Health Record

The process of using generative AI to listen to a conversation during
an appointment and create a summary that can be added to an electronic
health record (EHR) involves several technical and scientific
components. These components work together to convert spoken
words into text, analyze and understand the content, generate a
meaningful summary, and integrate it into the EHR system [20].
During the Covid-19 pandemic, Electronic Health Records (EHRs)
played a crucial role in managing patient information, facilitating
communication among healthcare providers, and supporting decision-
making processes. EHRs are digital versions of a patient's medical
history, including their diagnoses, treatments, medications, test results,
and other relevant health information. Covid-19 primarily spreads
through respiratory droplets when an infected person coughs, sneezes,
or talks [21], [22]. Common symptoms include fever, cough, shortness
of breath, fatigue, loss of taste or smell, and muscle aches. Some
individuals may be asymptomatic carriers, which contributed to the
rapid and wide-spread transmission.
The first step in this process is speech recognition. The conversation
between the healthcare provider and the patient is captured using a

118 | P a g e J. Adv. Analytics Healthc. Manage.

JAAHM
Journal of Advanced Analytics in
Healthcare Management

microphone or audio recording device. Automatic speech recognition

(ASR) technology is then employed to convert the spoken words into
text. ASR algorithms analyze the audio waveform, detect speech
segments, and transcribe them into written text [6]. This enables
further processing and analysis of the conversation.
Once the speech is transcribed into text, natural language processing
(NLP) techniques come into play. NLP algorithms are utilized to
process and understand the content of the conversation. These
algorithms analyze the structure and meaning of the text, including
identifying key phrases, entities, and relationships between words and
sentences. NLP helps in extracting relevant information from the
conversation and preparing it for further analysis.

Figure 1. Generative AI in electronic health record

A crucial subtask of NLP in this context is named entity recognition

(NER). NER focuses on identifying and categorizing named entities
within the text, such as patient names, medical conditions, medications,
procedures, and other relevant information [23]. NER algorithms rely
on machine learning models trained on large annotated datasets to
recognize and classify these entities accurately. By identifying and
categorizing these entities, the AI system can better understand the
context of the conversation.

119 | P a g e J. Adv. Analytics Healthc. Manage.

JAAHM
Journal of Advanced Analytics in
Healthcare Management

Contextual understanding is essential for generating a meaningful

summary of the conversation. This involves analyzing the sequence of
sentences, identifying the main topics, and capturing the relevant
details. Advanced NLP models, such as transformer-based architectures
can be used to provide a comprehensive understanding of the
conversation [24]. These models have been trained on vast amounts of
text data and can generate contextually relevant summaries.
Once the context is understood, the generative AI model generates a
concise summary of the conversation. Text summarization techniques
can vary depending on the specific approach used. Extractive
summarization involves selecting important sentences or phrases from
the original text, while abstractive summarization involves generating
new sentences that capture the essence of the conversation. The choice
of summarization technique depends on the requirements and
preferences of the healthcare provider or the EHR system.
The generated summary needs to be integrated into the patient's
electronic health record. This integration can be done through an
application programming interface (API) or a direct integration with
the EHR system. The summary is typically added as a structured or
unstructured note, depending on the EHR's capabilities and
requirements. This ensures that the information is readily accessible to
healthcare providers and can contribute to the patient's medical history.
Implementing such a system requires a combination of machine
learning techniques, substantial training data, and rigorous evaluation.
The machine learning models need to be trained on diverse and
representative datasets to ensure accurate recognition and
understanding of the conversation. Rigorous evaluation is necessary to
measure the system's performance, including its accuracy and its ability
to comply with healthcare regulations and standards.
Ensuring privacy and compliance with healthcare regulations is of
paramount importance [25]. The AI system should handle sensitive
patient information securely and follow established protocols for data
protection. Compliance with regulations such as the Health Insurance
Portability and Accountability Act (HIPAA) is crucial to protect patient
confidentiality and privacy [26], [27].
Furthermore, ongoing monitoring and refinement of the AI system are
necessary to improve its performance over time. The system should be
continually evaluated and updated to adapt to different medical
specialties and contexts. The feedback from healthcare providers and
patients can help identify areas for improvement and refine the system's
capabilities.
120 | P a g e J. Adv. Analytics Healthc. Manage.
JAAHM
Journal of Advanced Analytics in
Healthcare Management

The process of using generative AI to listen to a conversation during

an appointment and create a summary for an electronic health record
involves a series of technical and scientific components. These
components encompass speech recognition, natural language
processing, named entity recognition, contextual understanding, text
summarization, and integration with the EHR system. By combining
these components and adhering to stringent evaluation and privacy
measures, healthcare providers can leverage the power of AI to enhance
the efficiency and accuracy of their record-keeping processes while
maintaining patient confidentiality and compliance with healthcare
regulations.

Simplifying medical language

Below are the detailed descriptions of how generative AI can simplify
complex medical language into summaries that patients can
understand. The first step in the process is data collection. A large
dataset of medical documents is gathered, including research papers,
clinical notes, patient records, and other relevant sources. These
documents should contain complex medical language and terminology,
serving as a diverse and representative sample for training the
generative AI model.
Next, the collected data undergoes preprocessing. This involves
cleaning and removing irrelevant information, formatting the text, and
standardizing the document structure. By doing so, the data is prepared
for further analysis, ensuring consistency and coherence in the
subsequent steps.

Figure 2. Simplifying medical terminologies with Generative AI

121 | P a g e J. Adv. Analytics Healthc. Manage.

JAAHM
Journal of Advanced Analytics in
Healthcare Management

The training data preparation step splits the preprocessed data into two
sets: a training set and a validation set. The training set is used to train
the generative AI model, while the validation set is used to evaluate its
performance. This separation helps assess the model's ability to
generalize to new data. The model selection and architecture phase
involve choosing an appropriate generative AI model, such as a
transformer-based language model. The model's architecture is
configured, and hyperparameters, such as the number of layers, hidden
units, attention mechanisms, and other relevant settings, are defined.
Training the generative AI model is a crucial step where the model
learns to understand complex medical language and extract meaningful
information from the text. This process involves optimizing the model's
parameters to minimize the difference between the generated

122 | P a g e J. Adv. Analytics Healthc. Manage.

JAAHM
Journal of Advanced Analytics in
Healthcare Management

summaries and the target summaries, which represent the desired

simplified versions of the medical documents.
To evaluate the trained model's performance, the validation set is used.
Metrics such as BLEU score, ROUGE score, or human evaluation can
be employed to assess how well the generated summaries align with the
intended meaning of the original medical documents. This evaluation
helps identify areas where the model can be further improved.
If the evaluation results are not satisfactory, the model undergoes a
fine-tuning process. This may involve adjusting hyperparameters,
modifying the training data, or altering the model architecture. Fine-
tuning is an iterative process that helps enhance the model's
performance and align it more closely with the desired outcome.
Once the generative AI model produces summaries that meet the
desired quality standards, it is ready for deployment in a production
environment. This could be a web application, mobile app, or any other
platform where patients can access the generated summaries.
In the user interaction phase, patients can input complex medical
documents into the application or provide access to their medical
records. The generative AI model then processes the input text and
generates simplified summaries that are understandable to patients.
Summary generation is a key step where the deployed model applies
natural language generation techniques to transform complex medical
language into patient-friendly summaries. This involves extracting key
information, simplifying terminology, and ensuring the content
remains accurate and easily comprehensible for patients.
The generated summaries are presented to patients through a user
interface in the output presentation phase. Depending on the design of
the application, the summaries can be displayed as plain text,
highlighted key points, or structured information, making it easier for
patients to grasp the essential information from their medical
documents.
Collecting feedback from patients regarding the generated summaries
is essential for continuous improvement. This feedback helps identify
areas where the summaries can be further enhanced to better meet
patients' needs. By iterating based on this feedback, the generative AI
model can be refined, leading to improved quality and understandability
of the summaries.
The process of using generative AI to simplify complex medical
language into patient-friendly summaries involves data collection,

123 | P a g e J. Adv. Analytics Healthc. Manage.

JAAHM
Journal of Advanced Analytics in
Healthcare Management

preprocessing, training, evaluation, fine-tuning, deployment, user

interaction, summary generation, output presentation, and feedback
and iteration. Through this comprehensive workflow, generative AI
can assist in making medical information more accessible and
understandable for patients.

Wearable:
IoT and Sensor Networks: With the advent of the Internet of Things
(IoT), sensors are becoming even more prevalent as they enable devices
to collect and share data over the internet [28], [29]. These sensors
can be embedded in various objects, enabling smart and connected
systems.
In the first step of the technical sequence, users wear smartwatches or
wearables that are equipped with various sensors, including heart rate
monitors, accelerometers, and GPS trackers. These sensors
continuously collect data related to the user's health and physical
activities, such as heart rate, step count, sleep patterns, and location.
The collected data is stored locally on the smartwatch or wearable
device, ensuring that the information is readily available for further
processing.
Following data collection, the smartwatch or wearable device
establishes a connection, either wirelessly or through a smartphone, to
transfer the collected data to the cloud [30]. This ensures that the data
is securely transmitted and accessible from anywhere. The data is sent
to a cloud-based server or a data storage system, where it can be
processed and analyzed effectively.
Once the data reaches the cloud, it undergoes preprocessing to remove
noise, correct anomalies, and ensure data quality [31]. Various
preprocessing techniques are employed, including filtering,
normalization, and data transformation. These techniques help in
refining the collected raw data, making it suitable for further analysis
and interpretation.
With the preprocessed data at hand, generative AI algorithms come
into play. Sophisticated techniques such as deep learning models or
generative adversarial networks (GANs) are employed to analyze the
data. The generative AI model is trained on a vast amount of labeled
data to learn patterns, correlations, and relationships within the
collected information. Through this analysis, the model generates
valuable insights and predictions.
Personalized Care Recommendations: The generated insights and
predictions are utilized to provide personalized care recommendations

124 | P a g e J. Adv. Analytics Healthc. Manage.

JAAHM
Journal of Advanced Analytics in
Healthcare Management

to the user. Taking into account the user's health or weight

management needs, the generative AI model suggests specific actions,
interventions, or recommendations. These recommendations can be
related to personalized exercise plans, diet suggestions, sleep
optimization techniques, or reminders for medication or hydration. By
tailoring the recommendations to individual user needs, the system
aims to optimize the user's well-being.
To ensure effective delivery of the personalized care recommendations,
various channels are utilized. These can include mobile applications,
smartwatch interfaces, or web platforms. The recommendations are
presented to the user as notifications, alerts, or detailed reports,
depending on the user's preferences and the capabilities of the
smartwatch or wearable device. The goal is to provide the
recommendations in a format that is easily accessible and convenient
for the user.
Users actively engage with the smartwatch or wearable device to
provide feedback on the recommendations they receive. This
interaction can take the form of accepting or rejecting a
recommendation, rating its effectiveness, or reporting any issues or
concerns. User feedback is collected and incorporated into the system
to improve future recommendations and enhance the overall user
experience. By actively involving users in the feedback loop, the system
can continuously learn and adapt to individual preferences and
requirements.
By following this sequence flow, generative AI can effectively collect
and analyze data from smartwatches and wearables. Through the
analysis process [32], the system generates personalized care
recommendations tailored to suit individual user needs. This approach
aims to enhance the user's well-being by leveraging the power of data
and artificial intelligence to provide actionable insights and support for
healthy living.

125 | P a g e J. Adv. Analytics Healthc. Manage.

JAAHM
Journal of Advanced Analytics in
Healthcare Management

Figure 3. Generative AI for personalized healthcare

Conclusion
Generative AI, also known as generative adversarial networks (GANs),
is a cutting-edge technology that holds immense potential in various
domains. At its core, generative AI refers to a class of machine learning
algorithms that aim to create new and original content by learning from
existing data. Unlike traditional AI models that focus on classification
or prediction, generative AI focuses on the creative aspect of machine
learning.
Generative AI models consist of two main components: a generator and
a discriminator [33], [34]. The generator generates new data samples,

126 | P a g e J. Adv. Analytics Healthc. Manage.

JAAHM
Journal of Advanced Analytics in
Healthcare Management

such as images, music, or text, while the discriminator evaluates the

authenticity of these samples by differentiating between the generated
data and the real data. Through an iterative process, the generator aims
to create increasingly realistic samples that can deceive the
discriminator. This adversarial training mechanism enables the
generator to learn and improve over time, producing high-quality and
coherent outputs.
Personalized healthcare, also known as precision medicine, is a
transformative approach that leverages advances in genomics, data
analytics, and technology to tailor medical treatments and
interventions to individual patients. By considering an individual's
unique genetic makeup, lifestyle factors, and medical history,
personalized healthcare aims to provide targeted and more effective
healthcare interventions, ultimately improving patient outcomes.
The integration of technology and personalized healthcare is evident in
the rise of digital health solutions. Mobile applications, wearable
devices, and remote monitoring technologies have become increasingly
popular tools for capturing real-time health data. These technologies
enable individuals to actively participate in their healthcare
management, providing continuous streams of data on vital signs,
physical activity, sleep patterns, and more. Healthcare providers can
leverage this data to gain a deeper understanding of a patient's health
status, identify early warning signs, and provide timely interventions.
Moreover, telemedicine platforms enable remote consultations and
virtual care, facilitating access to specialized healthcare services
regardless of geographic location.
Generative AI, with its ability to create new and original content, has
made significant advancements in the healthcare industry, particularly
in areas such as electronic health records (EHRs), medical languages,
and personalized patient care. By harnessing the power of generative
AI, healthcare professionals can streamline data management, improve
communication, and provide more tailored and effective care to patients.
One of the areas where generative AI has shown great promise is in the
development and management of electronic health records. EHRs
contain a wealth of patient information, including medical histories, test
results, diagnoses, and treatment plans. However, extracting relevant
and actionable insights from these records can be challenging due to
the sheer volume of data. Generative AI algorithms can analyze EHR
data to identify patterns and relationships that may not be readily
apparent to human reviewers. This can help in predicting disease
outcomes, identifying risk factors, and suggesting personalized
treatment plans based on similar patient cases. By automating the
127 | P a g e J. Adv. Analytics Healthc. Manage.
JAAHM
Journal of Advanced Analytics in
Healthcare Management

analysis of EHRs, generative AI can save valuable time for healthcare

professionals and enhance the quality of care delivered to patients.
Generative AI also holds tremendous potential in facilitating medical
languages, which can often be complex and specialized. Medical
professionals rely on accurate and efficient communication to exchange
information and make informed decisions. However, medical
terminology and jargon can pose challenges for effective
communication, especially across different specialties and languages.
Generative AI models can be trained on vast amounts of medical
literature, research papers, and clinical notes to generate coherent and
contextually relevant medical language. This can assist healthcare
professionals in generating accurate clinical reports, providing patient
education materials, and even enabling real-time language translation
during international medical collaborations. By leveraging generative
AI, medical language barriers can be overcome, leading to improved
collaboration and enhanced patient care.
Personalized patient care is a key focus of healthcare, and generative AI
plays a vital role in tailoring treatments to individual patients. With
access to patient data, including genetic information, medical history,
and lifestyle factors, generative AI models can assist healthcare
providers in making more informed decisions regarding treatment
plans. These models can analyze large datasets to identify patterns and
correlations between patient characteristics and treatment outcomes.
By leveraging generative AI, healthcare professionals can generate
personalized treatment recommendations, predict the efficacy of
different interventions, and optimize care plans based on individual
patient needs. This leads to improved patient outcomes, reduced trial
and error in treatment selection, and more efficient healthcare delivery.

References
[1] I. Goodfellow et al., “Generative adversarial networks,” Commun.
ACM, vol. 63, no. 11, pp. 139–144, Oct. 2020.
[2] Z. Pan, W. Yu, X. Yi, A. Khan, F. Yuan, and Y. Zheng, “Recent
Progress on Generative Adversarial Networks (GANs): A Survey,”
IEEE Access, vol. 7, pp. 36322–36333, 2019.
[3] G. R. Bushe, “Generative Process, Generative Outcome: The
Transformational Potential of Appreciative Inquiry,” in
Organizational Generativity: The Appreciative Inquiry Summit and
a Scholarship of Transformation, vol. 4, Emerald Group Publishing
Limited, 2013, pp. 89–113.

128 | P a g e J. Adv. Analytics Healthc. Manage.

JAAHM
Journal of Advanced Analytics in
Healthcare Management

[4] S. Oh, Y. Jung, S. Kim, and I. Lee, “Deep generative design:

Integration of topology optimization and generative models,”
Journal of, 2019.
[5] J. Zhang, Z. Tang, Y. Xie, M. Ai, and W. Gui, “Generative
adversarial network-based image-level optimal setpoint calculation
for flotation reagents control,” Expert Syst. Appl., vol. 197, p.
116790, Jul. 2022.
[6] I. Vaccari, V. Orani, A. Paglialonga, E. Cambiaso, and M.
Mongelli, “A Generative Adversarial Network (GAN) Technique
for Internet of Medical Things Data,” Sensors , vol. 21, no. 11, May
2021.
[7] Y. Wang, H. Wang, L. Wei, S. Li, L. Liu, and X. Wang, “Synthetic
promoter design in Escherichia coli based on a deep generative
network,” Nucleic Acids Res., vol. 48, no. 12, pp. 6403–6412, Jul.
2020.
[8] X. Chen et al., “Variational Lossy Autoencoder,” arXiv [cs.LG],
08-Nov-2016.
[9] D. P. Kingma, T. Salimans, R. Jozefowicz, X. Chen, I. Sutskever,
and M. Welling, “Improved variational inference with inverse
autoregressive flow,” Adv. Neural Inf. Process. Syst., vol. 29, 2016.
[10] D. P. Kingma and P. Dhariwal, “Glow: Generative flow with
invertible 1x1 convolutions,” Adv. Neural Inf. Process. Syst., vol.
31, 2018.
[11] J. Parikh, J. Kozloski, and V. Gurev, “Integration of AI and
mechanistic modeling in generative adversarial networks for
stochastic inverse problems,” arXiv [stat.ML], 17-Sep-2020.
[12] Z. Cheng, D. Lee, and P. Tambe, “InnoVAE: Generative AI for
Understanding Patents and Innovation,” Available at SSRN
3868599, 01-Mar-2022.
[13] D. Foster, Generative Deep Learning, 2nd ed. Sebastopol, CA:
O’Reilly Media, 2022.
[14] A. Arora and A. Arora, “Generative adversarial networks and
synthetic patient data: current challenges and future perspectives,”
Future Healthc J, vol. 9, no. 2, pp. 190–193, Jul. 2022.
[15] E. B. Sloane and R. J. Silva, “Chapter 83 - Artificial intelligence in
medical devices and clinical decision support systems,” in Clinical
Engineering Handbook (Second Edition), E. Iadanza, Ed.
Academic Press, 2020, pp. 556–568.
[16] K. Thiagarajan, C. K. Dixit, M. Panneerselvam, C. A.
Madhuvappan, S. Gadde, and J. N. Shrote, “Analysis on the Growth
of Artificial Intelligence for Application Security in Internet of
Things,” in 2022 Second International Conference on Artificial
Intelligence and Smart Energy (ICAIS), 2022, pp. 6–12.
[17] G. Sinnapolu and S. Alawneh, “Integrating wearables with cloud-
based communication for health monitoring and emergency
assistance,” Internet of Things, vol. 1–2, pp. 40–54, Sep. 2018.
129 | P a g e J. Adv. Analytics Healthc. Manage.
JAAHM
Journal of Advanced Analytics in
Healthcare Management

[18] S. Durga, R. Nag, and E. Daniel, “Survey on Machine Learning and

Deep Learning Algorithms used in Internet of Things (IoT)
Healthcare,” in 2019 3rd International Conference on Computing
Methodologies and Communication (ICCMC), 2019, pp. 1018–
1022.
[19] D. Shin and Y. Hwang, “Integrated acceptance and sustainability
evaluation of Internet of Medical Things: A dual-level analysis,”
Internet Research, vol. 27, no. 5, pp. 1227–1254, Jan. 2017.
[20] A. Bohr and K. Memarzadeh, “Chapter 2 - The rise of artificial
intelligence in healthcare applications,” in Artificial Intelligence in
Healthcare, A. Bohr and K. Memarzadeh, Eds. Academic Press,
2020, pp. 25–60.
[21] D. Mallick, L. Goyal, P. Chourasia, M. R. Zapata, K. Yashi, and S.
Surani, “COVID-19 Induced Postural Orthostatic Tachycardia
Syndrome (POTS): A Review,” Cureus, vol. 15, no. 3, p. e36955,
Mar. 2023.
[22] M. Abdelghany et al., “CRT-200.08 outcomes of acute coronary
syndrome in patients with Coronavirus 2019 infection: A
systematic review and meta-analysis,” Cardiovascular
Interventions, vol. 15, no. 4_Supplement, pp. S29–S30, Feb. 2022.
[23] R. Florian and JOHNS HOPKINS UNIV BALTIMORE MD
CENTER FOR LANGUAGE AND SPEECH PROCESSING
(CLSP), “Named entity recognition as a house of cards: Classifier
stacking,” JOHNS HOPKINS UNIV BALTIMORE MD CENTER
FOR LANGUAGE AND SPEECH PROCESSING (CLSP), Jan.
2002.
[24] R. J. Chen, M. Y. Lu, T. Y. Chen, D. F. K. Williamson, and F.
Mahmood, “Synthetic data in machine learning for medicine and
healthcare,” Nat Biomed Eng, vol. 5, no. 6, pp. 493–497, Jun. 2021.
[25] A. Bodepudi and M. Reddy, “Spoofing Attacks and Mitigation
Strategies in Biometrics-as-a-Service Systems,” ERST, vol. 4, no.
1, pp. 1–14, Feb. 2020.
[26] V. S. Y. Cheng and P. C. K. Hung, “Health Insurance Portability
and Accountability Act (HIPPA) Compliant Access Control Model
for Web Services,” IJHISI, vol. 1, no. 1, pp. 22–39, Jan. 2006.
[27] P. Breese, W. Burman, C. Rietmeijer, and D. Lezotte, “The Health
Insurance Portability and Accountability Act and the informed
consent process,” Ann. Intern. Med., vol. 141, no. 11, pp. 897–898,
Dec. 2004.
[28] K. Thiagarajan, M. G.m, M. Porkodi, P. K., S. Gadde, and R.
Priyadharshini, “Application and Advancement of Sensor
Technology in Bioelectronics Nano Engineering,” in 2022
International Conference on Edge Computing and Applications
(ICECAA), 2022, pp. 841–845.
[29] G. G. Hallur, S. Prabhu, and A. Aslekar, “Entertainment in Era of
AI, Big Data & IoT,” in Digital Entertainment: The Next Evolution
130 | P a g e J. Adv. Analytics Healthc. Manage.
JAAHM
Journal of Advanced Analytics in
Healthcare Management

in Service Sector, S. Das and S. Gochhait, Eds. Singapore: Springer

Nature Singapore, 2021, pp. 87–109.
[30] S. Shashi Devi, S. Gadde, K. Harish, C. Manoharan, R. Mehta, and
S. Renukadevi, “IoT and image processing Techniques-Based
Smart Sericulture Nature System,” Indian J. Applied & Pure Bio,
vol. 37, no. 3, pp. 678–683, 2022.
[31] A. Bodepudi and M. Reddy, “Cloud-Based Gait Biometric
Identification in Smart Home Ecosystem,” International Journal of
Intelligent Automation and Computing, vol. 4, no. 1, pp. 49–59,
2021.
[32] A. Bodepudi and M. Reddy, “The Rise of Virtual Employee
Monitoring in Cloud and Its Impact on Hybrid Work Choice,”
Journal of Artificial Intelligence and Machine Learning in
Management, vol. 5, no. 1, pp. 25–50, 2021.
[33] G. Lee, H. Kim, J. Kim, S. Kim, J.-W. Ha, and Y. Choi, “Generator
Knows What Discriminator Should Learn in Unconditional GANs,”
in Computer Vision – ECCV 2022, 2022, pp. 406–422.
[34] K. Wang, C. Gou, Y. Duan, Y. Lin, X. Zheng, and F.-Y. Wang,
“Generative adversarial networks: introduction and outlook,”
IEEE/CAA Journal of Automatica Sinica, vol. 4, no. 4, pp. 588–598,
2017.

131 | P a g e J. Adv. Analytics Healthc. Manage.